Generative AI Engineer

Role Overview 

Build and deploy generative AI solutions using LLM fine-tuning, RAG architectures, and agentic AI systems.  

Responsibilities 

• Fine-tune large language models for domain-specific applications and use cases 
• Design and implement RAG (Retrieval Augmented Generation) pipelines with vector databases 
• Build agentic AI systems with autonomous decision-making and tool-using capabilities 
• Optimize LLM performance through prompt engineering, parameter tuning, and model selection 
• Develop and deploy production-ready GenAI applications and APIs 
• Evaluate model performance, conduct A/B testing, and iterate on solutions 
• Collaborate with cross-functional teams to integrate GenAI into products 

Requirements 

• Bachelor's degree in Computer Science, Engineering, AI/ML, or related field 
• Strong experience with LLM fine-tuning (LoRA, QLoRA, full fine-tuning, PEFT methods) 
• Proven expertise building RAG systems with vector databases and embeddings 
• Hands-on experience developing agentic AI solutions and multi-agent systems 
• Proficiency with LLM frameworks (LangChain, LlamaIndex, Haystack) 
• Experience with vector databases (Pinecone, Weaviate, ChromaDB, FAISS) 
• Strong Python programming skills 
• Understanding of transformer architectures and LLM APIs 

Preferred 

• Experience with distributed training and GPU optimization 
• Knowledge of MLOps, model deployment, and monitoring 
• Familiarity with Hugging Face ecosystem 
• Experience with prompt optimization and evaluation frameworks 
• Understanding of LLM safety, alignment, and guardrails 
• Background in NLP or deep learning research